Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Sentence Completion on HellaSwag

87.5Accuracy

Falcon-180B

52.067261.266170.46579.6639Oct 6, 2022May 7, 2023Dec 6, 2023Jul 7, 2024Feb 5, 2025Sep 6, 2025Apr 8, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2023.11
87.5--
2023.11
86.8--
2026.04
84.5--
2025.03
84.33--
2025.03
84.23--
2023.11
84--
2026.04
83.99--
2023.11
83.6--
2023.11
82--
2026.04
81.51--
2026.04
81.15--
2024.09
81.1--
2026.04
81.05--
2026.04
80.57--
2024.09
80.5--
2026.04
80.04--
2026.04
80.02--
2026.04
79.36--
2025.10
79.1--
2023.02
78.9--
2022.10
78.9--
2026.04
78.69--
2026.04
78.54--
2025.03
78.49--
2025.03
78.32--
2026.04
78.21--
2026.04
78.21--
2026.04
78.05--
2024.09
77.9--
2024.09
77.8--
2026.04
77.64--
2025.10
77.63--
2026.04
77.62--
2025.03
77.61--
2026.04
77.46--
2026.04
77.44--
2026.04
77.23--
2024.09
77.1--
2026.04
76.76--
2026.04
76.56--
2024.09
76.5--
2026.04
76.38--
2023.12
76.1--
2024.09
76--
2024.09
75.9--
2024.09
75.2--
2025.03
75.17--
2026.04
74.88--
2024.09
74.8--
2026.04
74.23--
2026.04
74.17--
2026.04
73.55--
2026.04
72.93--
2024.09
72.9--
2026.04
71.9--
2026.04
70.85--
2026.04
70.08--
2026.04
70.03--
2025.03
69.25--
2026.04
68.64--
2026.03
67.67--
2026.03
67.33--
2026.03
67.33--
2026.03
67.33--
2026.03
67--
2026.03
66.33--
2026.04
66.18--
2025.07
66.1--
2026.04
65.41--
2026.04
65.11--
2026.04
64.75--
2025.07
63.7--
2026.04
63.35--
2025.07
62.9--
2026.04
62.8--
2026.04
62.29--
2026.04
61.91--
2025.12
60.17--
2026.04
60.11--
2025.12
59.86--
2025.12
59.41--
2025.12
59.37--
2024.03
59.23--
2025.12
59.08--
2024.03
59.06--
2024.03
58.96--
2024.03
58.93--
2026.04
58.54--
2024.03
56.87--
2026.04
56.62--
2025.07
56.3--
2026.04
55.61--
2023.02
55--
2025.12
54.47--
2023.12
54.3--
2025.07
54.3--
2025.12
54.18--
2025.12
53.96--
2025.12
53.44--
2025.12
53.43--
Showing 100 of 285 rows